Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    reflect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orientation
    -0.09
    xBB
    -0.08
     GAS
    -0.06
     Acts
    -0.06
    _joint
    -0.06
    _SEQ
    -0.06
    Gam
    -0.06
    'a
    -0.06
     gang
    -0.06
    Fra
    -0.06
    POSITIVE LOGITS
    ertainty
    0.07
    .WebServlet
    0.06
    olio
    0.06
     ACM
    0.06
     özellikle
    0.06
    �
    0.06
    �
    0.06
    　　 　 　
    0.06
     (?
    0.06
    merican
    0.06
    Act Density 0.005%

    No Known Activations